Aiming at the problems of sensitive data leakage and unauthorised direct access faced during the storage and transmission of shared medical data, this paper proposes a new medical data security sharing scheme based on blockchain. Firstly, to ensure the security and randomness of the keys in the scheme, a new 4D-YG hyperchaotic key generator is designed. Secondly, self-expanding fractal Sierpinski triangle permutating operation is performed on medical images to achieve image decentring effect. Utilize a custom Order-Preserving Encryption (OPE) algorithm to diffuse it, ensuring consistency in pixel order before and after encryption. Subsequently, mix-bit triple normalized diffusion is performed on the images that have completed preliminary diffusion to enhance the resistance of privacy data within the image to attacks. Finally, the decryption permission for encrypted shared medical data is restricted through smart contracts in the blockchain. While achieving secure transmission of medical data, it enables hospitals to perform medical image segmentation and organ recognition diagnostics on shared data in an encrypted state, which is more in line with practical needs. According to performance test data, the proposed encryption algorithm can effectively resist differential attacks and frequency attacks, and the Number of Pixels Change Rate (NPCR) test results can reach the ideal value of 99.6094%.

As driverless technology advances, an immense amount of data will be generated, shared, and used between vehicles, users, and the cloud. This includes road conditions, GPS data, biometric data, which raises significant privacy concerns. This paper presents a secure authentication protocol and privacy protection framework based on chaotic biological cryptography for data sharing and storage in the Internet of Autonomous Vehicles(IoAV) framework. A biometric key generator is designed using single-modal multi-fingerprint feature-level reconstruction, allowing users to generate personalized private key pools. This protects biometric data in the cloud while ensuring revocability. By incorporating a nonlinear control function into the traditional three-dimensional Rucklidge chaotic system, a 4D-Yoz hyperchaotic system is created, ensuring secure key distribution and adherence to the “one time pad” principle. To verify the effectiveness of the chaos creature password and ensure the security of cloud-stored images, proposes an image encryption-storage algorithm based on the “$L_{\infty } $” metric and the semi-tensor product of the matrix, introducing the chaotic biological key. Experimental simulations and performance analysis show that this algorithm effectively secures image data in the Internet of Vehicles.

Traffic flow prediction is a key component of intelligent transportation systems (ITS), which helps to achieve efficient traffic management and planning. However, traffic data has complex spatio-temporal dependencies, and existing methods commonly use a static approach to model spatial dependencies, which has limitations in capturing dynamic spatio-temporal features. This paper proposes a traffic flow prediction model, named Bidirectional Cross-attention Spatio-Temporal Transformer (BCSTFormer). Initially, the model constructs a multidimensional feature embedding framework that integrates raw data, temporal periodicity, spatial location, and adaptive spatio-temporal embeddings, thereby enhancing the representation capability for complex traffic patterns. Subsequently, based on the Transformer encoder structure, a dual-branch parallel feature extraction architecture is designed, applying multi-head self-attention mechanisms separately in the temporal and spatial dimensions to effectively extract spatio-temporal features and improve computational efficiency. Finally, a bidirectional cross-attention feature fusion mechanism is employed to adaptively capture dynamic spatio-temporal dependencies through the bidirectional interaction of temporal and spatial features. Comparative experiments on four benchmark traffic datasets against ten state-of-the-art baseline models demonstrate that BCSTFormer achieves varying degrees of performance improvement in terms of MAE, RMSE, and MAPE.

Aiming at the problem that the traffic flow prediction model does not consider the road contextual correlation and implicit spatial dependency, a spatio-temporal traffic flow prediction model based on adaptive graph convolution (Transformer-Graph Convolutional Recurrent Network, TGCRN) is proposed, which extracts spatio-temporal features by using an encoder-decoder structure. The encoder part designs a convolutional multi-head self-attention mechanism to extract spatio-temporal features from both local and global perspectives, and uses a traffic pattern memory to augment the node’s pattern information to assist future prediction. The decoder part injects an adaptive graph convolution module into the recurrent neural network to capture both temporal and spatial dependencies and outputs future traffic scenarios. The model extracts the hidden spatial dependencies from the unknown graph structure without any a priori knowledge guidance and is able to model complex and dynamic spatio-temporal relationships. Extensive experiments based on four real traffic datasets confirm the effectiveness of our approach.

The rapid expansion of smart devices and applications within the Internet of Things (IoT) has resulted in an unprecedented surge of data, particularly image data, generated at the network edge. This imposes significant pressure on traditional centralized cloud computing paradigms and introduces severe challenges in terms of transmission efficiency and data security. To address these issues, edge computing-assisted IoT (EC-IoT) has emerged as a promising paradigm; however, the decentralized collection, transmission, and application of image data also exacerbate privacy risks. In this work, this article proposes a secure and lightweight EC-IoT architecture specifically tailored for efficient and resilient image transmission. Node registration and tagging mechanisms are introduced to enable identity verification without additional computational overhead, while Z-order encoding, strict hierarchical encryption, and node verification collectively ensure robust protection at minimal cost. Furthermore, we design an image encryption framework that integrates a novel 4-D cross-coupled chaotic map (4DCCM) with lattice-based cryptography, achieving strong encryption performance and seamless post-quantum security compatibility. Extensive experimental evaluations conducted on representative IoT application datasets—including Internet of Medical Things (IoMT), Internet of Vehicles (IoV), and Industrial IoT (IIoT) scenarios—demonstrate the effectiveness of the proposed scheme, achieving an average information entropy of 7.9993 while maintaining low computational overhead. This work contributes a secure, efficient, and post-quantum-resilient encryption framework, particularly suited for large-scale real-time transmission of visual information within next-generation IoT environments.

Traffic prediction is essential for intelligent transportation systems and smart city applications, yet existing spatio-temporal models face limitations.These include inadequate spatial feature extraction, neglect of spatial heterogeneity, and omission of factors like traffic speed and travel time.To address the above challenges, we propose a multimodal and multiview traffic flow prediction method called MMGCRN, which adaptively learns the spatio-temporal correlation features of multimodal traffic data.In MMGCRN, we design a spatial heterogeneous perception cross-attention module to model the spatial heterogeneous relationships of nodes.In addition, we use spatio-temporal embeddings to generate the dynamic feature correlation graph of nodes across time steps, which is combined with the topological graph and semantic graph and fed into the Multiview Graph Convolutional Recurrent Network (MGCRN) to extract the multi-dimensional correlations between nodes.We learn and fuse different modal traffic data through multiple MGCRN modules.Finally, experiments on two real-world datasets show that in 60-minute-ahead long-term forecasting, the MMGCRN model achieves a minimum improvement of 0.96% and a maximum improvement of 8.69% over baseline models.

Abstract The next Point of Interest (POI) recommendation is the core technology of smart city. Current state-of-the-art models attempt to improve the accuracy of the next POI recommendation by incorporating temporal and spatial intervals or by partitioning the POI coordinates into grids. However, they all overlook a detail that in real life, people always want to know where to go at an exact time point or after a specific time interval instead of aimlessly asking where to go next. Moreover, due to individual preferences, different users may visit different places at the same timestamp. Therefore, utilizing timestamp queries can enhance the personalized recommendation capability of the model and mitigate overfitting risks. These implies that using timestamp can achieve more precise recommendations. To the best of our knowledge, we are the first to use the next timestamp for next POI recommendation. In particular, we propose a Time-Stamp Cross Attention Network (TSCAN). TSCAN is a two-layer cross-attention network. The first layer, Time Stamp Cross Attention Block (TSCAB), uses cross-attention between the next timestamp and historical timestamps, and multiplies the attention scores on corresponding POI to predict the next POI that is most related to the history. The other layer, Cross Time Interval Aware Block (CTIAB), applies the time intervals between the next timestamp and historical timestamps to the POI obtained by TSCAB and historical POIs, allowing temporally adjacent POIs to have a greater similarity. Our model not only has a significant improvement in accuracy but also achieves the goal of personalized recommendation, effectively alleviating overfitting. We evaluate the proposed model with three real-world LBSN datasets, and show that TSCAN outperforms the state-of-the-art next POI recommendation models by 5~9%. TSCAN can not only recommend the next POI, but also recommend the possible POI to visit at any specific timestamp in the future.

High-precision three-dimensional road networks in open-pit mines play a crucial role in production planning, truck dispatching, and unmanned driving. Compared to urban road networks, the boundaries of open-pit mine roads are indistinct, with varying widths. The colors of these roads blend with the surrounding environments and they undergo rapid changes. Thus, accurately, efficiently, and timely obtaining mining road networks still faces many challenges. With the development and popularization of UAV technology, it is now possible to obtain real-time spatial data. We propose a HDMSCA (hybrid dilated multi-scale convolution attention) unit and design the D-SegNeXt network. This method offers several advantages. First, it reduces computational complexity and enlarges the receptive field through hybrid dilated convolution. Second, residual networks and multi-scale convolutions can extract local, distant, long, and narrow features, thereby enhancing the network’s ability to capture long-range dependencies. Additionally, we construct an OPM (open-pit mine road) dataset and test the models on it. The experimental results demonstrate that our model outperforms several benchmark networks in both image classification and road extraction. Our D-SegNeXt model achieves a Top-1 acc score of 82.8% on ImageNet-1k, an IoU score of 75.59% on the open-pit mine road dataset and an IoU score of 67.96% on the DeepGlobe Road Extraction Challenge dataset. Our dataset and code are available at https://github.com/orgs/D-SegNeXt/repositories.

Medical studies have found that Tumor Mutation Burden (TMB) is positively correlated with the efficacy of immunotherapy for Non-Small Cell Lung Cancer (NSCLC), and TMB value can predict the efficacy of targeted therapy and chemotherapy. However, the calculation of TMB value mainly depends on the Whole Exon Sequencing (WES) technology, which is usually expensive and takes too much time. To deal with this problem, this paper explores the connection between TMB and digital pathology images, predicting TMB using common clinical digital slices. We proposes RCA-MSAG, a deep learning model based on the Residual Coordinate Attention (RCA) structure and Multi-Scale Attention Guidance (MSAG) module, enhancing TMB prediction accuracy. The model takes ResNet-50, integrating Coordinate Attention (CA) and MSAG to extract critical information from lung cancer pathology. Using The Cancer Genome Atlas (TCGA) dataset, the model achieves 96.2% accuracy, 96.4% precision, 96.2% recall, and a 96.3% F1 score, outperforming mainstream models. This model shows promise in aiding clinical diagnoses and guiding TMB predictions.

Graph convolutional network (GCN) has rapidly developed in various fields due to its powerful modeling capability. However, most of the researches directly inherit the complex design of GCN, such as feature transformation and nonlinear activation, which lacks thorough ablation analysis on GCN. In addition, implicit feedback is not fully utilized and data sparsity is not well resolved, which are also shortcomings of current recommendation algorithms. To solve the above problems, this paper proposes a lightweight graph convolutional collaborative filtering (F-LightGCCF) recommendation approach incorporating social relationships. Firstly, it abandons the design of feature transformation and nonlinear activation in graph convolutional models and simplifies model training. Additionally, a series of intermediate feedback from users’ implicit negative feedback is generated by taking advantage of social networks, which improves the utilization of implicit negative feedback. Secondly, it can model the long-range dependencies between users and items by using the dual attention mechanism, aggregating the contribution values of neighboring nodes and the importance of the learning vectors in each layer of the graph convolution layer respectively. Lastly, the inner product operation is used to obtain the association score between users and items. Extensive experiment results on two real-world datasets show that F-LightGCCF outperforms existing state-of-the-art recommendation methods. Further ablation studies and analyses validate the efficiency and effectiveness of the F-LightGCCF model.

Abstract Personalized news recommendation is an important technology to help users obtain news information they are interested in and alleviate information overload. In recent years, news recommendation has been increasingly widely studied and has achieved remarkable success in improving the news reading experience of users. In this paper, we provide a comprehensive overview of personalized news recommendation approaches. Firstly, we introduce personalized news recommendation systems according to different needs and analyze the characteristics. And then, a three-part research framework on personalized news recommendation is put forward. Based on the framework, the knowledge and methods involved in each part are analyzed in detail, including news datasets and processing techniques, prediction models, news ranking and display. On this basis, we focus on news recommendation methods based on different types of graph structure learning, including user–news interaction graph, knowledge graph and social relationship graph. Lastly, the challenges of the current news recommendation are analyzed and the prospect of the future research direction is presented.

Due to the widespread uses of uncertain spatiotemporal data, web ordinary users have access to query these data in various ways. However, users often cannot accurately give query constraints so that the query results may be empty or very few. Traditional algorithms cannot be used to deal with uncertain spatiotemporal data because they have no relaxation query on spatiotemporal attributes. Therefore, in this paper, the authors propose new flexible query algorithms, which add relaxation query processing for spatiotemporal attributes. Considering that XML has great advantages in exchanging and representing spatiotemporal data, they propose an uncertain spatiotemporal data model based on XML. According to the different number of relaxing attributes, they give SingleRelaxation algorithm and MultipleRelaxation algorithm. In addition, a T-List structure is designed to quickly locate the nodes' positions of uncertain spatiotemporal data, and RSort algorithm is proposed to sort accurate query results and extended query results. The experimental results show the superiority of the approach.

Recommender system is the core to solve the problem of information overload. Meanwhile, non-IID (non-Independently Identically Distribution) recommender system shows its potential in improving recommendation quality and solving the problems such as sparsity and cold start. With the development of deep learning, recommendation has become a hot topic and a large number of studies have proved the effectiveness of deep learning in recommender system. In this work, we contribute a new multi-layer neural network framework, EACoupledCF (Enhanced Attention-based Coupled Collaborative Filtering), to perform collaborative filtering. The idea of EACoupledCF is to use an outer product to explicitly model the pairwise correlations between the dimensions of the embedding space, utilize the convolutional neural network and introduce spatial attention mechanism to learn high-order features between embedded dimensions. At the same time, it also proposes a novel model called DCCF (Deep Combination Collaborative Filtering) for implicit feedback learning in order to capture the interactive information better. In contrast to the existing neural recommendation models, the experimental results obtained on two real-word large datasets show the effectiveness of our proposed model.

Diversity point-of-interest recommendation system benefits users to broaden their interests, access and discover new interest points. This paper describes a Diversified and Personalized Point-Of-Interest Recommendation System (DP-POIRS) by leveraging the geo-social relationships between POIs. The system consists of three components. The first component - geo-social distance measuring component is used to construct a correlation matrix to describe the geo-social distance between points of interests. The second component -point-of-interest partition component, divides the interest points into diverse clusters by using the spectral clustering algorithm over the correlation matrix. The third component -personalized sorting component, finds out the user's favorite interest points from each cluster, and then sorts them into a list of recommendation by the use of matrix factorization algorithms.

Spatial database queries are often exploratory. The users often find that their queries return too many answers and many of them may be irrelevant. Based on the coupling relationships between spatial objects, this paper proposes a novel categorization approach which consists of two steps. The first step analyzes the spatial object coupling relationship by considering the location proximity and semantic similarity between spatial objects, and then a set of clusters over the spatial objects can be generated, where each cluster represents one type of user need. When a user issues a spatial query, the second step presents to the user a category tree which is generated by using modified C4.5 decision tree algorithm over the clusters such that the user can easily select the subset of query results matching his/her needs by exploring the labels assigned on intermediate nodes of the tree. The experiments demonstrate that our spatial object clustering method can efficiently capture both the semantic and location correlations between spatial objects. The effectiveness and efficiency of the categorization algorithm is also demonstrated.

Due to imprecise query intention, Web database users often use a limited number of keywords that are not directly related to their precise query to search information. Semantic approximate keyword query is challenging but helpful for specifying such query intent and providing more relevant answers. By extracting the semantic relationships both between keywords and keyword queries, this paper proposes a new keyword query approach which generates semantic approximate answers by identifying a set of keyword queries from the query history whose semantics are related to the given keyword query. To capture the semantic relationships between keywords, a semantic coupling relationship analysis model is introduced to model both the intra- and inter-keyword couplings. Building on the coupling relationships between keywords, the semantic similarity of different keyword queries is then measured by a semantic matrix. The representative queries in query history are identified and then a priori order of remaining queries corresponding to each representative query in an off-line preprocessing step is created. These representative queries and associated orders are then used to expeditiously generate top-k ranked semantically related keyword queries. We demonstrate that our coupling relationship analysis model can accurately capture the semantic relationships both between keywords and queries. The efficiency of top-k keyword query selection algorithm is also demonstrated.

Due to the insufficient knowledge of users about the database schema and content, most of them cannot easy to find appropriate keywords to express their query intentions. This paper proposes a novel approach, which can provide a list of keywords that semantically related to the set of given query keywords by analyzing the correlations between terms in database and query keywords. The suggestion would broaden the knowledge of users and help them to formulate more efficient keyword queries. To capture the correlations between terms in database and query keywords, a coupling relationship measuring method is proposed to model both the term intra- and intercouplings, which can reveal the explicit and implicit relationships between terms. For a given keyword query, based on the coupling relationships between terms, an order of terms in database is created for each query keyword and then the threshold algorithm (TA) is to expeditiously generate top-k ranked semantically related terms. The experiments demonstrate that our term coupling relationship measuring method can efficiently capture the semantic correlations between terms. The performance of top-k related term selection algorithm is also demonstrated.

Recently, keyword search has attracted a great deal of attention in an XML database. In many applications which backend data source powered by an XML database management system, keyword search because important to query XML data if the user does not know the structure or only knows the structure of XML partially. Given a keyword query, existing approaches first compute the lowest common ancestors (LCAs) or their variants of XML elements that contain the input keywords, and then identify the subtrees rooted at the LCAs as the answer. But this method doesn't satisfy the user's intention well enough. For users, information containing some keywords (not all keywords) may also be useful. In this paper, we solve this problem through applying relax structural queries during the XML keyword search procedure, and progressively to obtain the top-k answers of keyword proximity search though analyzing the semantic and structural information of the queries. We propose a transformation framework to derive the structural queries by analyzing the given keyword and the structural information of XML database. In addition, we propose a scoring method considering user's preference, and at last, we design an architecture (Rtop-k) to adaptively and efficiently identify the top-k relevant answers of a query. The performance of the technique as well as the recall and the precision were measured experimentally. These experiments indicate that our system is efficient enough and ranks quality results highly.

There may exist a specific relationship between the keywords if an XML multi-keywords search has more than one answers. Such relationship can be speculated by SLCA. This paper proposes a user-friendly Top-k keywords searching approach based on the relationship of keywords. The SLCA of a keyword search is first obtained by the LISA II algorithm. Then, the structure of SLCA is leveraged to speculate the relationship of keywords, i.e., the keyword search is translated into twig queries. Next, the relationship of keywords can be estimated by the structure of twig queries and these twig queries are ranked according to the relationships of keywords. Finally, all results of the ordered twig queries are obtained by TJFast algorithm. The experimental results demonstrated that the approach presented in this paper has the high precision, and can efficiently meet the user's needs as well.

To deal with the problem of too many answer elements returned from a XML repository in response to a user query, this paper proposes a personalized categorization approach which takes advantages of the user preferences to construct a categorization tree in order to reduce the information overload. The approach consists of two steps. The first step analyzes query history of all users in the system offline and generates a set of clusters over the XML elements, where each elements cluster represents one kind of user preference. When a user query coming, based on the element clusters, a categorization tree is generated automatically by using the C4.5 algorithm and presented to the user, such that the user can easily select the relevant elements matching his needs. Results of a preliminary user study demonstrate that the categorization method proposed has good categorization effectiveness and low searching cost.

How to quickly and cheaply construct Web ontologies has become a key technology to enable the Semantic Web. Classical ontologies are not sufficient for handling imprecise and uncertain information that is commonly found in many application domains. In this paper, we propose an approach for constructing fuzzy ontologies from fuzzy UML models, in which the fuzzy ontology consists of fuzzy ontology structure and instances. Firstly, the fuzzy UML model is investigated in detail, and a kind of formal definition of fuzzy UML models is proposed. Then, a kind of fuzzy ontology called fuzzy OWL DL ontology is introduced. Furthermore, we consider the fuzzy UML model and the corresponding fuzzy UML instantiations (i.e., object diagrams) simultaneously, and translate them into the fuzzy ontology structure and the fuzzy ontology instances, respectively. In addition, since a fuzzy OWL DL ontology is equivalent to a fuzzy Description Logic f-SHOIN(D) knowledge base, how the reasoning problems of fuzzy UML models (e.g., consistency, subsumption, equivalence, and redundancy) may be reasoned through reasoning mechanism of f-SHOIN(D) is investigated, which can help to construct fuzzy ontologies more exactly.

To deal with the problem of empty or too little answers returned from a Web database in response to a user query, this paper proposes a novel approach to provide relevant and ranked query results. Based on the user original query, we speculate how much the user cares about each specified attribute and assign a corresponding weight to it. This original query is then rewritten as an approximate query by relaxing the query criteria range. The relaxation order of all specified attributes and the relaxed degree on each specified attribute are varied with the attribute weights. For the approximate query results, we generate users' contextual preferences from database workload and use them to create a priori orders of tuples in an off-line preprocessing step. Only a few representative orders are saved, each corresponding to a set of contexts. Then, these orders and associated contexts are used at query time to expeditiously provide ranked answers. Results of a preliminary user study demonstrate that our query relaxation and results ranking methods can capture the user's preferences effectively. The efficiency and effectiveness of our approach is also demonstrated by experimental result.

Users often have vague or imprecise ideas when searching the Web database, thus they might like to issue fuzzy queries that consist of fuzzy terms or fuzzy relations for possibly retrieving. To deal with the problem of too many results returned from a Web database in response to a user fuzzy query, this paper proposes a novel approach to rank the fuzzy query results. Based on database workload, we firstly speculate the importance of each attribute and assign a corresponding weight to it. And then, based on fuzzy sets theory, a membership degree ranking method, which ranks the query results according to the tuple's satisfaction degree to the fuzzy query, is presented. Next, based on data and workload statistics and correlations, we present a relevance degree ranking method, which assigns a relevance score for each unspecified attribute value according to its corresponding attribute weight and its desirableness to the user. Results of preliminary experiments demonstrating the efficiency and efficacy of the ranking approach are presented.

To deal with the problem of too many results returned from a Web database in response to a user query, this paper proposes a novel approach, which takes advantage of the contextual preferences to precompute a few representative orders of tuples and uses them to expeditiously provide ranked answers factoring in the information contained in the query. Contextual preferences take the form that item i1 is preferred to item i2 with an interest degree in the context of X. This paper formally defines contextual preferences, provides algorithms for creating tuple orders, clustering orders and processing queries, and presents experimental results to show their efficiency.